index.py · about.md · case-studies.json · contact.json

AdINNtelligence: what should our next ad be?

September 18, 2026 · #agents #martech #innocean

Dealership marketing teams watch competitors by scrolling feeds, which doesn't scale and isn't systematic. AdINNtelligence automates the whole loop for automotive teams across 40+ brands.

1. Collect. Pull verified competitor ads from the Meta Ad Library over a rolling 24-hour window.
2. Classify. Use LLMs to extract models, offers and creative patterns.
3. Recommend. Turn those patterns into three evidence-backed recommendations for the dealer's next campaign.

Stack: FastAPI, React, Groq, Supabase and Redis, deployed on Vercel and Railway.

Code: github.com/Ashwin07Mishra/AdINNtelligence

← back to case studies

This is the plain-HTML version of this site — no JavaScript, CSS 2.1 only, built to render in Dillo.
Full version of this page · github · linkedin · resume.pdf · ashwin.mishra07@gmail.com